Electricity Load and Peak Forecasting: Feature Engineering, Probabilistic LightGBM and Temporal Hierarchies

被引：0

作者：

Rubattu, Nicolo ^{[1
]}

Maroni, Gabriele ^{[1
]}

Corani, Giorgio ^{[1
]}

机构：

[1] Dalle Molle Inst Artificial Intelligence IDSIA, USI SUPSI, CH-6962 Lugano, Switzerland

来源：

ADVANCED ANALYTICS AND LEARNING ON TEMPORAL DATA, AALTD 2023 | 2023年 / 14343卷

基金：

瑞士国家科学基金会;

关键词：

Load Forecasting; Feature engineering; Gradient Boosting; Hierarchical Forecasting; Forecast Reconciliation; MODEL;

D O I：

10.1007/978-3-031-49896-1_18

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We describe our experience in developing a predictive model that placed a high position in the BigDEAL Challenge 2022, an energy competition of load and peak forecasting. We present a novel procedure for feature engineering and feature selection, based on cluster permutation of temperatures and calendar variables. We adopted gradient boosting of trees and we enhanced its capabilities with trend modeling and distributional forecasts. We also included an approach to forecasts combination known as temporal hierarchies, which further improves the accuracy.

引用

页码：276 / 292

页数：17

共 50 条

[41] Feature Decoupling Peak-load Forecasting Model Considering Meteorological Cumulative Effect
Qin C.
Ding P.
Liu B.
Ju P.
Dianli Xitong Zidonghua/Automation of Electric Power Systems, 2022, 46 (06): : 66 - 72
[42] Feature selection for daily peak load forecasting using a neuro-fuzzy system
Son, Sung-Yong
Lee, Sang-Hong
Chung, Kyungyong
Lim, Joon S.
MULTIMEDIA TOOLS AND APPLICATIONS, 2015, 74 (07) : 2321 - 2336
[43] National-scale electricity peak load forecasting: Traditional, machine learning, or hybrid model?
Lee, Juyong
Cho, Youngsang
ENERGY, 2022, 239
[44] Short-Term Electricity Load Forecasting Based on Temporal Fusion Transformer Model
Pham Canh Huy
Nguyen Quoc Minh
Nguyen Dang Tien
Tao Thi Quynh Anh
IEEE ACCESS, 2022, 10 : 106296 - 106304
[45] Feature and model selection for day-ahead electricity-load forecasting in residential buildings
Kychkin, Aleksey, V
Chasparis, Georgios C.
ENERGY AND BUILDINGS, 2021, 249
[46] Feature and model selection for day-ahead electricity-load forecasting in residential buildings
Kychkin, Aleksey V.
Chasparis, Georgios C.
Energy and Buildings, 2021, 249
[47] Multidimensional Feature-Based Graph Attention Networks and Dynamic Learning for Electricity Load Forecasting
Huang, Chaokai
Du, Ning
He, Jiahan
Li, Na
Feng, Yifan
Cai, Weihong
ENERGIES, 2023, 16 (18)
[48] Neural-based electricity load forecasting using hybrid of GA and ACO for feature selection
Mansour Sheikhan
Najmeh Mohammadi
Neural Computing and Applications, 2012, 21 : 1961 - 1970
[49] Neural-based electricity load forecasting using hybrid of GA and ACO for feature selection
Sheikhan, Mansour
Mohammadi, Najmeh
NEURAL COMPUTING & APPLICATIONS, 2012, 21 (08): : 1961 - 1970
[50] GMDH-Based Semi-Supervised Feature Selection for Electricity Load Classification Forecasting
Yang, Lintao
Yang, Honggeng
Liu, Haitao
SUSTAINABILITY, 2018, 10 (01)

← 1 2 3 4 5 →